public Decoder(CodePageEncoding encoding)
{
if (encoding.CodePage == 50229)
{
throw new NotSupportedException(Environment.GetResourceString("NotSupported_CodePage50229"));
}
this.encoding = encoding;
lastByte = -1;
temp = new byte[2];
}
/*
* //ENCODINGFALLBACK
* internal static Encoding CreateDefaultEncoding(EncodingFallback encodingFallback) {
* Encoding enc;
* int codePage = Win32Native.GetACP();
*
* // For US English, we can save some startup working set by not calling
* // GetEncoding(int codePage) since JITting GetEncoding will force us to load
* // all the Encoding classes for ASCII, UTF7 & UTF8, & UnicodeEncoding.
* if (codePage == 1252) {
* enc = new CodePageEncoding(codePage, encodingFallback);
* }
* else
* enc = GetEncoding(codePage);
* return (enc);
* }
*/
internal static Encoding CreateDefaultEncoding()
{
Encoding enc;
int codePage = Win32Native.GetACP();
// For US English, we can save some startup working set by not calling
// GetEncoding(int codePage) since JITting GetEncoding will force us to load
// all the Encoding classes for ASCII, UTF7 & UTF8, & UnicodeEncoding.
if (codePage == 1252)
{
enc = new CodePageEncoding(codePage);
}
else
{
enc = GetEncoding(codePage);
}
return(enc);
}
private static Encoding GetEncodingRare(int codepage)
{
BCLDebug.Assert(codepage != 0 && codepage != 1200 && codepage != 1201 && codepage != 65001, "This code page (" + codepage + " isn't supported by GetEncodingRare!");
Encoding result;
switch (codepage)
{
case 1:
case 2:
case 3:
case 42:
// NOTENOTE :
// Win32 also allows the following special code page values. We won't allow them except in the
// CP_ACP case.
// #define CP_ACP 0 // default to ANSI code page
// #define CP_OEMCP 1 // default to OEM code page
// #define CP_MACCP 2 // default to MAC code page
// #define CP_THREAD_ACP 3 // current thread's ANSI code page
// #define CP_SYMBOL 42 // SYMBOL translations
throw new ArgumentException(String.Format(Environment.GetResourceString("Argument_CodepageNotSupported"), codepage), "codepage");
case 65000:
result = UTF7;
break;
case 20127:
result = ASCII;
break;
case ENC50229:
throw new NotSupportedException(Environment.GetResourceString("NotSupported_CodePage50229"));
default:
result = new CodePageEncoding(codepage);
break;
}
return(result);
}
/*
* //ENCODINGFALLBACK
* internal unsafe int CallUnicodeToBytes(char[] chars, int charIndex, int charCount, byte[] bytes, int byteIndex, int byteCount, out bool usedDefaultChar) {
* //
* // For MLang, there is no way to detect if default characters are used during the conversion.
* // So always set used default char to true.
* //
* usedDefaultChar = true;
* return (nativeUnicodeToBytes(m_pIMLangConvertCharsetFromUnicode, chars, charIndex, charCount, bytes, byteIndex, byteCount));
* }
*
* internal unsafe int CallBytesToUnicode(byte[] bytes, int byteIndex, int byteCount, char[] chars, int charIndex, int charCount) {
* return (nativeBytesToUnicode(m_pIMLangConvertCharsetToUnicode, bytes, byteIndex, out byteCount, chars, charIndex, charCount));
* }
*/
public override int GetCharCount(byte[] bytes, int index, int count)
{
if (bytes == null)
{
throw new ArgumentNullException("bytes",
Environment.GetResourceString("ArgumentNull_Array"));
}
if (index < 0 || count < 0)
{
throw new ArgumentOutOfRangeException((index < 0 ? "index" : "count"),
Environment.GetResourceString("ArgumentOutOfRange_NeedNonNegNum"));
}
if (bytes.Length - index < count)
{
throw new ArgumentOutOfRangeException("bytes",
Environment.GetResourceString("ArgumentOutOfRange_IndexCountBuffer"));
}
int charCount = 0;
int result;
int dwMode = 0;
if (count < 3 && IsISCIICodePage(CodePage))
{
// Because of the way that MLang handles DLL-based code page, we will always fail (and get AgrumentException as a result)
// when the byteCount is less than 3.
// Therfore, let's call Win32 to convert these bytes directly.
result = CodePageEncoding.BytesToUnicodeNative(CodePage, bytes, index, count, null, 0, 0);
}
else
{
result = nativeBytesToUnicode(CodePage, bytes, index, out count, null, 0, charCount, ref dwMode);
}
return(result);
}
internal static Encoding CreateDefaultEncoding() {
Encoding enc;
int codePage = Win32Native.GetACP();
// For US English, we can save some startup working set by not calling
// GetEncoding(int codePage) since JITting GetEncoding will force us to load
// all the Encoding classes for ASCII, UTF7 & UTF8, & UnicodeEncoding.
if (codePage == 1252) {
enc = new CodePageEncoding(codePage);
}
else
enc = GetEncoding(codePage);
return (enc);
}
private static Encoding GetEncodingRare(int codepage)
{
BCLDebug.Assert(codepage != 0 && codepage != 1200 && codepage != 1201 && codepage != 65001, "This code page ("+codepage+" isn't supported by GetEncodingRare!");
Encoding result;
switch (codepage) {
case 1:
case 2:
case 3:
case 42:
// NOTENOTE :
// Win32 also allows the following special code page values. We won't allow them except in the
// CP_ACP case.
// #define CP_ACP 0 // default to ANSI code page
// #define CP_OEMCP 1 // default to OEM code page
// #define CP_MACCP 2 // default to MAC code page
// #define CP_THREAD_ACP 3 // current thread's ANSI code page
// #define CP_SYMBOL 42 // SYMBOL translations
throw new ArgumentException(String.Format(Environment.GetResourceString("Argument_CodepageNotSupported"), codepage), "codepage");
case 65000:
result = UTF7;
break;
case 20127:
result = ASCII;
break;
case ENC50229:
throw new NotSupportedException(Environment.GetResourceString("NotSupported_CodePage50229"));
default:
result = new CodePageEncoding(codepage);
break;
}
return result;
}
/// <include file='doc\Encoding.uex' path='docs/doc[@for="Encoding.GetEncoding1"]/*' />
public static Encoding GetEncoding(int codepage)
{
//
// NOTENOTE: If you add a new encoding that can be get by codepage, be sure to
// add the corresponding item in EncodingTable.
// Otherwise, the code below will throw exception when trying to call
// EncodingTable.GetDataItem().
//
if (codepage < 0 || codepage > 65535) {
throw new ArgumentOutOfRangeException(
"codepage", String.Format(Environment.GetResourceString("ArgumentOutOfRange_Range"),
0, 65535));
}
Encoding result = null;
if (encodings != null)
result = (Encoding)encodings[codepage];
if (result == null) {
lock (typeof(Encoding)) {
if (encodings == null) encodings = new Hashtable();
if ((result = (Encoding)encodings[codepage])!=null) {
return result;
}
// Special case the commonly used Encoding classes here, then call
// GetEncodingRare to avoid loading classes like MLangCodePageEncoding
// and ASCIIEncoding. ASP.NET uses UTF-8 & ISO-8859-1.
switch (codepage) {
case 0:
result = CreateDefaultEncoding();
break;
case 1200:
result = Unicode;
break;
case 1201:
result = BigEndianUnicode;
break;
case 1252:
case ISO_8859_1:
result = new CodePageEncoding(codepage);
break;
case 65001:
result = UTF8;
break;
default:
result = GetEncodingRare(codepage);
break;
}
encodings.Add(codepage, result);
}
}
return result;
}
private static Encoding GetEncodingRare(int codepage)
{
BCLDebug.Assert(codepage != 0 && codepage != 1200 && codepage != 1201 && codepage != 65001, "This code page (" + codepage + " isn't supported by GetEncodingRare!");
Encoding result;
switch (codepage)
{
case 1:
case 2:
case 3:
case 42:
// NOTENOTE YSLin:
// Win32 also allows the following special code page values. We won't allow them except in the
// CP_ACP case.
// #define CP_ACP 0 // default to ANSI code page
// #define CP_OEMCP 1 // default to OEM code page
// #define CP_MACCP 2 // default to MAC code page
// #define CP_THREAD_ACP 3 // current thread's ANSI code page
// #define CP_SYMBOL 42 // SYMBOL translations
throw new ArgumentException(String.Format(Environment.GetResourceString("Argument_CodepageNotSupported"), codepage), "codepage");
case 65000:
result = UTF7;
break;
case 20127:
result = ASCII;
break;
case ISO_8859_1:
result = Latin1;
break;
case ISOKorean:
result = new MLangCodePageEncoding(ISOKorean, ISOKorean_SIZE);
break;
case ChineseSimp:
result = new MLangCodePageEncoding(ChineseSimp, ChineseSimp_SIZE);
break;
case ISCIIAsseme:
case ISCIIBengali:
case ISCIIDevanagari:
case ISCIIGujarathi:
case ISCIIKannada:
case ISCIIMalayalam:
case ISCIIOriya:
case ISCIIPanjabi:
case ISCIITamil:
case ISCIITelugu:
result = new MLangCodePageEncoding(codepage, ISCII_SIZE);
break;
case ISO2022JP:
result = new MLangCodePageEncoding(ISO2022JP, ISO2022JP_SIZE);
break;
case ENC50221:
result = new MLangCodePageEncoding(ENC50221, ENC50221_SIZE);
break;
case ENC50222:
result = new MLangCodePageEncoding(ENC50222, ENC50222_SIZE);
break;
case ENC50227:
result = new MLangCodePageEncoding(ENC50227, ENC50227_SIZE);
break;
case EUCJP:
result = new MLangCodePageEncoding(EUCJP, EUCJP_SIZE);
break;
case GB18030:
result = new GB18030Encoding();
break;
case EUCCN:
result = new MLangCodePageEncoding(EUCCN, EUCCN_SIZE);
break;
case ENC50229:
throw new NotSupportedException(Environment.GetResourceString("NotSupported_CodePage50229"));
default:
result = new CodePageEncoding(codepage);
break;
}
return(result);
}
// Returns an Encoding object for a given code page.
//
// YSLin Make this internal for now until we decide the final spec of EncodingFallback
/*
* //ENCODINGFALLBACK
* internal static Encoding GetEncoding(int codepage, EncodingFallback encodingFallback)
* {
* //
* // NOTENOTE: If you add a new encoding that can be get by codepage, be sure to
* // add the corresponding item in EncodingTable.
* // Otherwise, the code below will throw exception when trying to call
* // EncodingTable.GetDataItem().
* //
* if (codepage < 0 || codepage > 65535) {
* throw new ArgumentOutOfRangeException(
* "codepage", String.Format(Environment.GetResourceString("ArgumentOutOfRange_Range"),
* 0, 65535));
* }
* Encoding result = null;
* if (encodings != null)
* result = (Encoding)encodings[codepage];
* if (result == null) {
* lock (typeof(Encoding)) {
* if (encodings == null) encodings = new Hashtable();
* if ((result = (Encoding)encodings[codepage])!=null) {
* return result;
* }
* switch (codepage) {
* case 0:
* if (encodingFallback != null) {
* return (CreateDefaultEncoding(encodingFallback));
* }
* result = Default;
* break;
* case 1:
* case 2:
* case 3:
* case 42:
* // NOTENOTE YSLin:
* // Win32 also allows the following special code page values. We won't allow them except in the
* // CP_ACP case.
* // #define CP_ACP 0 // default to ANSI code page
* // #define CP_OEMCP 1 // default to OEM code page
* // #define CP_MACCP 2 // default to MAC code page
* // #define CP_THREAD_ACP 3 // current thread's ANSI code page
* // #define CP_SYMBOL 42 // SYMBOL translations
* throw new ArgumentException(String.Format(Environment.GetResourceString("Argument_CodepageNotSupported"), codepage), "codepage");
* case 1200:
* result = Unicode;
* break;
* case 1201:
* result = BigEndianUnicode;
* break;
* case 65000:
* result = UTF7;
* break;
* case 65001:
* result = UTF8;
* break;
* case 20127:
* result = ASCII;
* break;
* case ISOKorean:
* case ChineseSimp:
* case ISCIIAsseme:
* case ISCIIBengali:
* case ISCIIDevanagari:
* case ISCIIGujarathi:
* case ISCIIKannada:
* case ISCIIMalayalam:
* case ISCIIOriya:
* case ISCIIPanjabi:
* case ISCIITamil:
* case ISCIITelugu:
* case ISO2022JP:
* if (encodingFallback != null) {
* return (new MLangCodePageEncoding(codepage, encodingFallback));
* }
* result = new MLangCodePageEncoding(codepage);
* break;
* case EUCJP:
* result = new EUCJPEncoding();
* break;
* default:
* if (encodingFallback != null) {
* return (new CodePageEncoding(codepage, encodingFallback));
* }
* result = new CodePageEncoding(codepage);
* break;
* }
* encodings.Add(codepage, result);
* }
*
* }
* return result;
* }
*/
/// <include file='doc\Encoding.uex' path='docs/doc[@for="Encoding.GetEncoding1"]/*' />
public static Encoding GetEncoding(int codepage)
{
//
// NOTENOTE: If you add a new encoding that can be get by codepage, be sure to
// add the corresponding item in EncodingTable.
// Otherwise, the code below will throw exception when trying to call
// EncodingTable.GetDataItem().
//
if (codepage < 0 || codepage > 65535)
{
throw new ArgumentOutOfRangeException(
"codepage", String.Format(Environment.GetResourceString("ArgumentOutOfRange_Range"),
0, 65535));
}
Encoding result = null;
if (encodings != null)
{
result = (Encoding)encodings[codepage];
}
if (result == null)
{
lock (typeof(Encoding)) {
if (encodings == null)
{
encodings = new Hashtable();
}
if ((result = (Encoding)encodings[codepage]) != null)
{
return(result);
}
// Special case the commonly used Encoding classes here, then call
// GetEncodingRare to avoid loading classes like MLangCodePageEncoding
// and ASCIIEncoding. ASP.NET uses UTF-8 & ISO-8859-1.
switch (codepage)
{
case 0:
result = CreateDefaultEncoding();
break;
case 1200:
result = Unicode;
break;
case 1201:
result = BigEndianUnicode;
break;
case 1252:
result = new CodePageEncoding(codepage);
break;
case 65001:
result = UTF8;
break;
default:
result = GetEncodingRare(codepage);
break;
}
encodings.Add(codepage, result);
}
}
return(result);
}
static Console() {
// For console apps, the console handles are set to values like 3, 7,
// and 11 OR if you've been created via CreateProcess, possibly -1
// or 0. -1 is definitely invalid, while 0 is probably invalid.
// Also note each handle can independently be bad or good.
// For Windows apps, the console handles are set to values like 3, 7,
// and 11 but are invalid handles - you may not write to them. However,
// you can still spawn a Windows app via CreateProcess and read stdout
// and stderr.
// So, we always need to check each handle independently for validity
// by trying to write or read to it, unless it is -1.
// Delay initialize Console.In until someone uses it.
// Set up Console.Out
Encoding outEnc = null;
Stream s = OpenStandardOutput(_DefaultConsoleBufferSize);
if (s == Stream.Null) {
#if _DEBUG
if (CheckOutputDebug())
_out = MakeDebugOutputTextWriter("Console.Out: ");
else
#endif
_out = TextWriter.Synchronized(StreamWriter.Null);
}
else {
// To avoid loading about 7 classes, don't call Encoding.GetEncoding(int)
outEnc = new CodePageEncoding(GetConsoleOutputCPNative());
StreamWriter stdout = new StreamWriter(s, outEnc, _DefaultConsoleBufferSize);
stdout.AutoFlush = true;
stdout.Closable = !IsStreamAConsole(Win32Native.STD_OUTPUT_HANDLE);
_out = TextWriter.Synchronized(stdout);
}
// Set up Console.Error
s = OpenStandardError(_DefaultConsoleBufferSize);
if (s == Stream.Null) {
#if _DEBUG
if (CheckOutputDebug())
_error = MakeDebugOutputTextWriter("Console.Error: ");
else
#endif
_error = TextWriter.Synchronized(StreamWriter.Null);
}
else {
if (outEnc == null)
outEnc = new CodePageEncoding(GetConsoleOutputCPNative());
StreamWriter stderr = new StreamWriter(s, outEnc, _DefaultConsoleBufferSize);
stderr.AutoFlush = true;
stderr.Closable = !IsStreamAConsole(Win32Native.STD_ERROR_HANDLE);
_error = TextWriter.Synchronized(stderr);
}
}
public Decoder(CodePageEncoding encoding) {
if (encoding.CodePage==50229) {
throw new NotSupportedException(Environment.GetResourceString("NotSupported_CodePage50229"));
}
this.encoding = encoding;
lastByte = -1;
temp = new byte[2];
}
public override int GetChars(byte[] bytes, int byteIndex, int byteCount, char[] chars, int charIndex)
{
if (bytes == null || chars == null)
{
throw new ArgumentNullException((bytes == null ? "bytes" : "chars"),
Environment.GetResourceString("ArgumentNull_Array"));
}
if (byteIndex < 0 || byteCount < 0)
{
throw new ArgumentOutOfRangeException((byteIndex < 0 ? "byteIndex" : "byteCount"),
Environment.GetResourceString("ArgumentOutOfRange_NeedNonNegNum"));
}
if (bytes.Length - byteIndex < byteCount)
{
throw new ArgumentOutOfRangeException("bytes",
Environment.GetResourceString("ArgumentOutOfRange_IndexCountBuffer"));
}
if (charIndex < 0 || charIndex > chars.Length)
{
throw new ArgumentOutOfRangeException("charIndex",
Environment.GetResourceString("ArgumentOutOfRange_Index"));
}
if (byteCount == 0)
{
return(0);
}
// There are cases that a call to nativeBytesToUnicode() may generate an empty string. For example, if
// bytes only contain a lead byte.
// Therefore, we should allow charIndex to be equal to chars.Length.
int charCount = chars.Length - charIndex;
int result;
int dwMode = 0;
if (byteCount < 3 && IsISCIICodePage(CodePage))
{
if (charIndex == chars.Length)
{
throw new ArgumentException(Environment.GetResourceString("Argument_ConversionOverflow"));
}
// Because of the way that MLang handles DLL-based code page, we will always fail (and get AgrumentException as a result)
// when the byteCount is less than 3.
// Therfore, let's call Win32 to convert these bytes directly.
result = CodePageEncoding.BytesToUnicodeNative(CodePage, bytes, byteIndex, byteCount,
chars, charIndex, chars.Length - charIndex);
if (result == 0)
{
throw new ArgumentException(Environment.GetResourceString("Argument_ConversionOverflow"));
}
}
else
{
result = nativeBytesToUnicode(
CodePage,
bytes, byteIndex, out byteCount,
chars, charIndex, charCount, ref dwMode);
}
return(result);
}
